Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to requests and recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by "that" (agreement/recommendation)

    np_acts-logits-general · gemini-2.0-flash

    insists that/imperative that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Roskov
    -1.13
    WithIOException
    -0.90
    findpost
    -0.88
    VIAF
    -0.81
     فريبيس
    -0.81
    Rüyada
    -0.80
    ientôt
    -0.78
    IVEREF
    -0.77
     '\\;'
    -0.77
    ScopeManager
    -0.76
    POSITIVE LOGITS
     that
    0.70
     be
    0.67
     we
    0.56
    go
    0.51
     mellett
    0.50
     not
    0.48
    we
    0.47
     keep
    0.44
     cuno
    0.44
    Be
    0.43
    Act Density 0.200%

    No Known Activations